Skillv1.0.0

ClawScan security

Game Design FTUE Hero Journey Audit · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

BenignApr 21, 2026, 12:06 PM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: This is an instruction-only FTUE audit skill whose instructions, files, and requirements are internally consistent with its stated purpose and do not request credentials or perform installs.
Guidance: This skill is instruction-only and appears coherent with its stated purpose. Before using, avoid uploading sensitive or proprietary game builds, private analytics data, or user PII unless you intend to share them for the audit. If you want limited-risk testing, provide anonymized screenshots, short video clips, or a written description of the FTUE flow rather than full source builds. Note: the skill can be invoked by the agent per platform defaults — that’s normal — but you should still review any requests the agent makes for files or external uploads before consenting.

Purpose & Capability: okThe name/description (FTUE Hero's Journey audit) matches the SKILL.md and reference files; no unrelated binaries, env vars, or config paths are requested.
Instruction Scope: okSKILL.md contains only audit guidance and output structure; it does not instruct the agent to read system files, access external endpoints, or exfiltrate credentials. It stays within the stated purpose of analyzing onboarding flows.
Install Mechanism: okNo install spec and no code files — the lowest-risk form (instruction-only). Nothing will be downloaded or executed on the host by the skill itself.
Credentials: okThe skill requires no environment variables, credentials, or config paths; requested data is limited to the audit input the user supplies, which is proportionate to its function.
Persistence & Privilege: okalways is false and autonomous invocation is the platform default; the skill does not request persistent or elevated privileges or attempt to modify other skills or system settings.